Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Gas Saturated Sandstone Reservoirs Characterization through Probabilistic Seismic Inversion Using Bayesian Neural Networks

Scientific Contributions Oil and Gas · Vol. 49 No. 3 (2026) · hlm. 567–592

DOI
10.29017/scog.v49i3.2138
ISSN
2541-0520, 2089-3361
Terbit
2026-09-30
Penerbit
Testing Center for Oil and Gas LEMIGAS
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Shallow gas-saturated sandstone reservoirs are prevalent throughout Indonesia, presenting highly lucrative economic prospects that are often hindered by complex geological heterogeneities. Characterization of these reservoirs typically relies on deterministic seismic inversion methods. However, the inherent non-uniqueness of such approaches yields singular solutions devoid of uncertainty quantification. This study proposes a robust probabilistic seismic inversion methodology utilizing a Convolutional Bayesian Neural Network (BNN). By incorporating Monte Carlo (MC) dropout, which forces the stochastic deactivation of hidden nodes during training, the algorithm successfully generates a comprehensive ensemble of predictive realizations. The proposed framework is evaluated using 2D pre-stack synthetic angle gathers (0 to 45°) across two scenarios: a baseline layer-cake model and a structurally complex faulted model incorporating random noise to simulate field-acquired data. Using seismic amplitudes and low-frequency models to simultaneously predict porosity, clay volume, and water saturation, the BNN demonstrates exceptional predictive accuracy on the baseline model, yielding an average Root Mean Square Error (RMSE) of 0.03 and a coefficient of determination (R2) of 0.9. When applied to the complex faulted model, the predictive fidelity naturally degraded (average R2 of 0.7 to 0.8; RMSE of 0.09 to 0.15), consistent with the inherent challenges of noise-contaminated data. Furthermore, a comparative analysis against a conventional model-based deterministic inversion reveals that while the deterministic approach better delineates fault architectures via horizon constraints, the BNN framework yields superior quantitative fidelity. Notably, the BNN successfully overcomes the systematic underestimation of porosity inherent in the deterministic acoustic impedance-to-porosity conversion process. The stochastic inversion explicitly produces 2D petrophysical cross-sections detailing the P10, P90, and mean distributions extracted from 50 realizations. Given their high fidelity, the mean distributions are directly applicable for reservoir characterization. Crucially, the probabilistic P10 and P90 boundary percentiles facilitate a comprehensive assessment of in-place hydrocarbon volumes. This study are currently limited to synthetic validation, and subsequent validation with real-field data is necessary before the approach can be practically applied.

Kata kunci

Jaringan kolaborasi para penulis

17 penulis · 51 tautan kepenulisan bersama · 24 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Syarif Hidayatullah State Islamic University Jakarta
  • Bandung Institute of Technology
  • Universitas Negeri Padang
  • Indonesia University of Education
  • University of Indonesia
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Hakim Afif PutraSyarif Hidayatullah State Islamic University Jakarta2
SuwondoSyarif Hidayatullah State Islamic University Jakarta2
Muhammad NafianSyarif Hidayatullah State Islamic University Jakarta2
Widi AtmokoAfiliasi tidak diketahui2
Mitra DjamalBandung Institute of Technology1
Ramli RamliUniversitas Negeri Padang1
Freddy HaryantoBandung Institute of Technology1
Ahmad AminudinIndonesia University of Education1
Khairurrijal KhairurrijalBandung Institute of Technology1
Ambran HartonoSyarif Hidayatullah State Islamic University Jakarta1
Cuk ImawanUniversity of Indonesia1
Tati ZeraSyarif Hidayatullah State Islamic University Jakarta1
Bahrul UlumSyarif Hidayatullah State Islamic University Jakarta1
Jarea Yurika LubisSyarif Hidayatullah State Islamic University Jakarta1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.lemigas.esdm.go.id/index.php/SCOG/oai, pertama di-harvest 10 Nov 2026, terakhir terlihat 10 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Gas Saturated Sandstone Reservoirs Characterization through Probabilistic Seismic Inversion Using Bayesian Neural Networks</dc:title>
	<dc:creator xml:lang="en">Sanjaya, Edi</dc:creator>
	<dc:creator xml:lang="en">Riyadi, Praditiyo</dc:creator>
	<dc:creator xml:lang="en">Rahman, Fadhlur</dc:creator>
	<dc:subject xml:lang="en">probabilistic inversion</dc:subject>
	<dc:subject xml:lang="en">Bayesian Neural Network</dc:subject>
	<dc:subject xml:lang="en">petrophysical properties</dc:subject>
	<dc:subject xml:lang="en">gas sandstone</dc:subject>
	<dc:description xml:lang="en">Shallow gas-saturated sandstone reservoirs are prevalent throughout Indonesia, presenting highly lucrative economic prospects that are often hindered by complex geological heterogeneities. Characterization of these reservoirs typically relies on deterministic seismic inversion methods. However, the inherent non-uniqueness of such approaches yields singular solutions devoid of uncertainty quantification. This study proposes a robust probabilistic seismic inversion methodology utilizing a Convolutional Bayesian Neural Network (BNN). By incorporating Monte Carlo (MC) dropout, which forces the stochastic deactivation of hidden nodes during training, the algorithm successfully generates a comprehensive ensemble of predictive realizations. The proposed framework is evaluated using 2D pre-stack synthetic angle gathers (0 to 45°) across two scenarios: a baseline layer-cake model and a structurally complex faulted model incorporating random noise to simulate field-acquired data. Using seismic amplitudes and low-frequency models to simultaneously predict porosity, clay volume, and water saturation, the BNN demonstrates exceptional predictive accuracy on the baseline model, yielding an average Root Mean Square Error (RMSE) of 0.03 and a coefficient of determination (R2) of 0.9. When applied to the complex faulted model, the predictive fidelity naturally degraded (average R2 of 0.7 to 0.8; RMSE of 0.09 to 0.15), consistent with the inherent challenges of noise-contaminated data. Furthermore, a comparative analysis against a conventional model-based deterministic inversion reveals that while the deterministic approach better delineates fault architectures via horizon constraints, the BNN framework yields superior quantitative fidelity. Notably, the BNN successfully overcomes the systematic underestimation of porosity inherent in the deterministic acoustic impedance-to-porosity conversion process. The stochastic inversion explicitly produces 2D petrophysical cross-sections detailing the P10, P90, and mean distributions extracted from 50 realizations. Given their high fidelity, the mean distributions are directly applicable for reservoir characterization. Crucially, the probabilistic P10 and P90 boundary percentiles facilitate a comprehensive assessment of in-place hydrocarbon volumes. This study are currently limited to synthetic validation, and subsequent validation with real-field data is necessary before the approach can be practically applied.</dc:description>
	<dc:publisher xml:lang="en">Testing Center for Oil and Gas LEMIGAS</dc:publisher>
	<dc:date>2026-09-30</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.lemigas.esdm.go.id/index.php/SCOG/article/view/2138</dc:identifier>
	<dc:identifier>10.29017/scog.v49i3.2138</dc:identifier>
	<dc:source xml:lang="en">Scientific Contributions Oil and Gas; Vol. 49 No. 3 (2026); 567-592</dc:source>
	<dc:source xml:lang="id">Scientific Contributions Oil and Gas; Vol 49 No 3 (2026); 567-592</dc:source>
	<dc:source>2541-0520</dc:source>
	<dc:source>2089-3361</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.lemigas.esdm.go.id/index.php/SCOG/article/view/2138/1776</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2026 Copyright by Authors. Published by LEMIGAS</dc:rights>
	<dc:rights xml:lang="en">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>